Short Message Service (SMS) is a widely used communication medium for mobile applications, such as banking, social networking, and e-commerce. Applications of SMS services also include real-time broadcasting messages, such as notification of natural disasters (e.g., bushfires and hurricane) and terrorist attacks, and sharing the current whereabouts to other users, such as notifying urgent business meeting information, transmitting quick information in the battlefield to multiple users, notifying current location to our friends and sharing market information. However, traditional SMS is not designed with security in mind (e.g., messages are not securely sent). It is also possible to extract international mobile subscriber identity of the mobile user. In the literature, there is no known protocol that could enable secure transmission of SMS from one user to multiple users simultaneously. In this paper, we introduce a batch verification authentication and key agreement protocol, BVPSMS, which provides end-to-end message security over an insecure communication channel between different mobile subscribers. Specifically, the proposed protocol securely transmits SMS from one mobile user to many other users simultaneously. The reliability of the protocol is discussed along with an algorithm to detect malicious user requests in a batch. We then evaluate the performance of the proposed protocol in terms of communication and computation overheads, protocol execution time, and batch and re-batch verification times. The impacts of the user mobility, and the time, space and cost complexity analysis are also discussed. We then present a formal security proof of the proposed protocol. To the best of our knowledge, this is the first provably-secure batch verification protocol that delivers end-to-end SMS security using symmetric keys.

Mobile operators offer a wide range of value-added services (VAS) to their subscribers (i.e., mobile users), which in turn generates around 15% of the telecommunication industry revenue. However, simultaneous VAS requests from a large number of mobile devices to a single server or a cluster in an internet-of-things (IoT) environment could result in an inefficient system, if these requests are handled one at a time as the present traditional cellular network scenario is. This will not only slow down the server's efficiency but also adversely impacts the performance of the network. The current (insecure) practice of transmitting user identity in plaintext also results in traceability. In this paper, we introduce the first known protocol designed to efficiently handle multiple VAS requests at one time, as well as ensuring the secure delivery of the services to a large number of requesting mobile users. The proposed batch verification protocol (BAS-VAS) is capable of authenticating multiple simultaneous requests received by a large number of mobile users. We demonstrate that the protocol preserves user privacy over the network. The provider's servers ensure the privacy of the requested service's priority by performing sorting over encrypted integer data. The simulation results also demonstrate that the proposed protocol is lightweight and efficient in terms of communication and computation overheads, protocol execution time, and batch and re-batch verification delay. Specifically, we perform batch and re-batch verification (after detecting and removing malicious requests from the batch) for multiple requests in order to improve the overall efficiency of the system, as well as discussing time, space and cost complexity analysis, along with the security proof of our protocol using Proverif.

The Evolved Packet System-based Authentication and Key Agreement (EPS-AKA) protocol of the long-term evolution (LTE) network does not support Internet of Things (IoT) objects and has several security limitations, including transmission of the object’s (user/device) identity and key set identifier in plaintext over the network, synchronization, large overhead, limited identity privacy, and security attack vulnerabilities. In this article, we propose a new secure and efficient AKA protocol for the LTE network that supports secure and efficient communications among various IoT devices as well as among the users. Analysis shows that our protocol is secure, efficient, and privacy preserved, and reduces bandwidth consumption during authentication.

Nowadays, short message service (SMS) is being used in many daily life applications, including healthcare monitoring, mobile banking, mobile commerce, and so on. But when we send an SMS from one mobile phone to another, the information contained in the SMS transmit as plain text. Sometimes this information may be confidential like account numbers, passwords, license numbers, and so on, and it is a major drawback to send such information through SMS while the traditional SMS service does not provide encryption to the information before its transmission. In this paper, we propose an efficient and secure protocol called EasySMS, which provides end-to-end secure communication through SMS between end users. The working of the protocol is presented by considering two different scenarios. The analysis of the proposed protocol shows that this protocol is able to prevent various attacks, including SMS disclosure, over the air modification, replay attack, man-in-the-middle attack, and impersonation attack. The EasySMS protocol generates minimum communication and computation overheads as compared with existing SMSSec and PK-SIM protocols. On an average, the EasySMS protocol reduces 51% and 31% of the bandwidth consumption and reduces 62% and 45% of message exchanged during the authentication process in comparison to SMSSec and PK-SIM protocols respectively. Authors claim that EasySMS is the first protocol completely based on the symmetric key cryptography and retain original architecture of cellular network.

In this paper, we introduce an efficient batch oriented authentication and key agreement protocol for value added services named VAS-AKA to authenticate multiple requests sent from different mobile stations at a time. The reliability of the protocol is discussed along with the algorithm to detect one or more invalid mobile user(s) in a batch. The security analysis and performance evaluation in terms of communication and computation overhead, batch and re-batch verification delay is presented. Using this protocol, the authentication server efficiently able to verify authentication requests sent from multiple mobile users.

The use of heuristics and metaheuristic approach has grown rapidly in solving combinatorial optimization problems as they provide an optimal or a sub optimal solution in reasonable time. In this paper, we proposed a metaheuristic approach to solve 2D-Strip packing problem. We have also carried out a comparative study with a pool of crossover operators to find the best coupled one with our approach. The exhaustive testing on a benchmark dataset shows the efficiency of the approach is to solve large instances in reasonable time. Amongst the various crossover operators used maximal preservative crossover is found to be most suitable. The conclusion is supported by the extensive testing on several instances from the literature.

This paper presents a genetic programming (GP) based approach for designing classifiers with feature selection using a modified crossover operator. The proposed GP methodology simultaneously selects a good subset of features and constructs a classifier using the selected features. For a c-class problem, it provides a classifier having c trees. To overcome the difficulties with standard crossover operator, we have used a crossover operator which discovers the best possible crossover site for a subtree and attains higher fitness values while processing fewer individuals. We have tested our method on several datasets having large number of features. We have compared the performance of our method with results available in the literature and found that the proposed method generates good results.

In this paper, a Binary Neural Network Classifier (BNNC) is proposed in which hidden layer training is done in parallel. Learning Algorithm for the BNNC is described, which is based on the principle of Fast Covering Learning Algorithm (FCLA) proposed by Wang and Chaudhari. The BNNC offers high degree of parallelism in hidden layer formation. Each module in the hidden layer of BNNC is exposed to the patterns of only one class. For achieving better accuracy, issue of overlapped classes are also handled. The method is tested on few benchmark datasets, accuracies are within the acceptable range. Due to parallelism at hidden layer level, training time is decreased, therefore, it can be used for voluminous realistic database. An analytical formulation is developed to evaluate the number of hidden layer neurons, it is in the O(log(N)), where N represents the number of inputs.

In this paper we propose a novel Support Vector Machine(SVM) based approach for noisy data removal from datasets. It is observed that the instability present in the dataset greatly affects the overall performance of the any classifier. Hence, we propose a methodology for removal of such instabilities. In the proposed approach, we proceed by determining the clusters formed using support equilibrium points. Then analyzing, each cluster and remove the noisy data using the accuracy factor. Our approach, provide an important feature for reducing the training time and reducing the misclassification test error. The methodology if adopted for classifiers before the training phase will enhance the efficiency of the system. The approach is being tested on benchmark dataset, and it is observed that the efficiency of classifier increased by 15-20%.

Learning of (context-free) grammar rules that are based on alignment between texts of a given collection of sentences has attracted the attention of many researchers. We define and study the alignment profile and formulate fuzzy similarity of alignment profiles for a given collection of sentences. Using the fuzzy-similarity-based profile alignment, we give a methodology to formulate stochastic context-free grammar (CFG) rules. We introduce profile-alignment-based dynamic sentence similarity threshold to formulate the rules of stochastic CFG. The proposed methodology is tested using Child Language Data Exchange System (CHILDES) dataset of sentences. The benefits of our approach are experimentally demonstrated. Since our approach does not make use of any domain knowledge, it is expected to be useful in wide variety of applications requiring model construction.

Conventional recurrent neural networks (RNNs) have difficulties in learning long-term dependencies. To tackle this problem, we propose an architecture called segmented-memory recurrent neural network (SMRNN). A symbolic sequence is broken into segments and then presented as inputs to the SMRNN one symbol per cycle. The SMRNN uses separate internal states to store symbol-level context, as well as segment-level context. The symbol-level context is updated for each symbol presented for input. The segment-level context is updated after each segment. The SMRNN is trained using an extended real-time recurrent learning algorithm. We test the performance of SMRNN on the information latching problem, the "two-sequence problem" and the problem of protein secondary structure (PSS) prediction. Our implementation results indicate that SMRNN performs better on long-term dependency problems than conventional RNNs. Besides, we also theoretically analyze how the segmented memory of SMRNN helps learning long-term temporal dependencies and study the impact of the segment length.

This paper presents an approach for designing classifiers for a multiclass problem using Genetic Programming (GP). The proposed approach takes an integrated view of all classes when GP evolves. An individual of the population will be represented using multiple trees. The GP is trained with a set of N training samples in steps. A concept of unfitness of a tree is used in order to improve genetic evolution. Weak trees having poor performance are given more chance to participate in the genetic operations, and thus improve themselves. In this context, a new mutation operation called nondestructive directed point mutation is used, which reduces the destructive nature of mutation operation. The approach is being demonstrated by experimenting on some datasets.

To construct decision boundaries for two-class classification, SVM approach is attractive due to its efficiency. However, this approach is useful for 2-class classification and when the classes (labels) for the data are known. In practice, we have collection of labeled as well as unlabelled data, and it gives rise to semi-supervised classification problem. In this paper, we give a semi-supervised classification algorithm based on support vector machine (SVM). Novel feature of our approach is the formulation of spherical decision boundaries and the exploitation of the dynamical system associated with support function to obtain the number of clusters. The experimental results on a few well-known datasets, namely, Iris dataset, Shuttle landing control dataset, Wisconsin Breast cancer dataset, glass dataset, and balance scale dataset, indicate that our approach results in satisfactory classification as well as generalization accuracy.

Protein secondary structure (PSS) prediction is an important topic in bioinformatics. Our study on a large set of non-homologous proteins shows that long-range interactions commonly exist and negatively affect PSS prediction. Besides, we also reveal strong correlations between secondary structure (SS) elements. In order to take into account the long-range interactions and SS-SS correlations, we propose a novel prediction system based on cascaded bidirectional recurrent neural network (BRNN). We compare the cascaded BRNN against another two BRNN architectures, namely the original BRNN architecture used for speech recognition as well as Pollastri's BRNN that was proposed for PSS prediction. Our cascaded BRNN achieves an overall three state accuracy Q3 of 74.38\%, and reaches a high Segment OVerlap (SOV) of 66.0455. It outperforms the original BRNN and Pollastri's BRNN in both Q3 and SOV. Specifically, it improves the SOV score by 4-6%.

We introduce a similarity measure, called alignment profile similarity, for the learning of context-free grammar from given language samples. Based on the alignment profile similarity, an alignment learning framework for grammatical inference is proposed. Alignment profile similarity is used to improve alignments, and therefore increase the quality of the rules identified. The experiments show that the proposed methods improve performance in terms of the percentage of correctly generated grammar rules.

In theoretical computer science, it is well-established fact that Turing model (and its equivalent models like Chomsky's phrase structured grammar model, or recursively enumerable functions) is a most general model for computation. Many biologically inspired computing paradigms such as traditional neural networks, genetic algorithms, evolutionary computing frameworks etc., aim at addressing the problem of automatic generation of algorithmic solutions for many computationally difficult problems. Various soft computing models have complementary capabilities. This motivates us to investigate systematic framework for their integration. In this paper, we give an overview of the computational capabilities of some soft computing models, and make some observations about their integration

In Turing Machines, the input string can be of size n, where n is any natural number. The memory tape of the Turing Machine may store symbols which in general, may depend on this parameter n. Using hard-limiter neurons, earlier we introduced a framework for simulating a Turing machine [5]. In our earlier schemes [5], for accessing one symbol on memory tape having m symbols, we needed the number of operations that depend (at least logarithmically) on m. In this paper, we introduce a framework for constant time access of any symbol on memory tape.

Majority of the actions in army are hierarchical and occur simultaneously with some other action. Mission of an echelon is sub-divided into sub-missions which are assigned to the lower echelon. These lower echelons pursue their missions simultaneously. To apply reinforcement learning to such highly concurrent actions' domain as military, we propose a concurrent options model for a set of temporally extended actions that may not terminate at the same time and trigger the next transition without any regard for the other sub-options. We provide formal representation of the model.

In this paper, we share some of our observations for designing and implementing a shopping mall design (called Hikegaya) with 3D technology. We constructed Hikegaya using Hypertext Preprocessor (PHP), MySQL, Adobe Photoshop 7, Discreet 3D Studio Max 6, and ParallelGraphics VrmlPad. The methodology for design is discussed. With the existing technologies and with our use for prototype implementation experience of Hikegaya, we conclude that 3D applications for e-commerce are feasible.

In this paper, we propose a hybrid RNN/HMM system for protein secondary structure prediction, where each secondary structure segment is approximated by a second-order recurrent neural network embedded in the state of a segmental hidden Markov model. We evaluate the hybrid system on the RS126 and CB396 sets and obtain promising results.

A computational efficient artificial neural network for adaptive channel equalization in a digital communication system with 4-QAM signal constellation is purposed. We proposed a single layer Chebyshev neural network (ChNN) by expanding the input pattern by Chebyshev polynomials. Performance comparison was carried out through extensive computer simulations with two other neural networks: an MLP and a functional link ANN together with a linear LIMS-based equalizer. It is shown that the ChNN provides satisfactory results in terms of convergence rate, MSE floor and BER over a wide range of EVR, SNR and nonlinear conditions with substantial reduction in the computational complexity.

The analysis of DNA microarray expression data has become an important subject in bioinformatics. Scientists have adopted different approaches to select the informative genes those can distinguish different types of cancers. In this paper, we show the use of a dimension reduction technique such as singular value decomposition (SVD) to capture the genes with similar patterns. We propose a novel method of selection of feature genes based on information loss using SVD. To assign the samples to known classes, we design a multi-layer perceptron-based classifier with reduced dimensional input vectors. We provide performance comparison between different selection methods in terms of classification rate

We propose a fast training algorithm called fast constructive-covering approach (FCCA) for neural network construction based on geometrical expansion. Parameters are updated according to the geometrical location of the training samples in the input space, and each sample in the training set is learned only once. By doing this, FCCA is able to avoid iterations and is much faster than traditional training algorithms. Given an input sequence in an arbitrary order, FCCA learns 'easy' samples first and the 'confusing' samples are easily learned after these 'easy' samples. This sample reordering process is done on the fly based on geometrical concept. A comparison of this method with a few other methods on the well-known Iris data set is given.

We introduce a method for construction of a Turing machine using binary, hard-limiter neurons with integer weights and thresholds. We identify the problem of potentially infinite fan-in needed for read units. We give two approaches to tackle this problem. The first approach organizes the neural read units in the form of a pipeline. The second approach organizes the read units in tree-structure. We identify trade-off in time performance and design complexity for these two approaches.

We propose a constructive unsupervised learning algorithm (CULA) for Boolean neural networks based on geometrical expansion. CULA constructs two-layered (input and output layer) neural networks. We visualize output neurons in terms of hyperspheres. CULA results in fast learning because it determines whether to add a new coming vertex to a neuron by its geometrical location, not by iterant computation. We illustrate CULA by using 101 instances in zoo database of Richard Forsyth, and compare our unsupervised clustering with clustering by biological experts given in the zoo database.

We introduce a novel learning algorithm called multi-core learning (MCL) to construct a neural network for implementing a Boolean link training algorithm (BLTA) and expand-and-truncate learning (ETL). MCL needs a fewer hidden neurons. MCL also needs less number of operations for obtaining the connection weights and thresholds for hidden layer. We illustrate this advantage of our method (over ETL and BLTA) through an example.

A key problem in Binary Neural Network learning is to decide bigger linear separable subsets. In this paper we prove some lemmas about linear separability. Based on these lemmas, we propose Multi-Core Learning (MCL) and Multi-Core Expand-and-Truncate Learning (MCETL) algorithms to construct Binary Neural Networks. We conclude that MCL and MCETL simplify the equations to compute weights and thresholds, and they result in the construction of simpler hidden layer. Examples are given to demonstrate these conclusions.

A new knowledge representation model, known as fuzzy deduction graph (FDG), is introduced in this paper. An FDG can represent a knowledge base containing the fuzzy propositions and fuzzy rules. In an FDG, a systematic method of finding the fuzzy reasoning path (FRP) is given which is based on Dijkstra's shortest path framework. The FRP gives a relationship between the antecedent (source) proposition and consequent (goal) proposition, such that the consequent proposition is reached with the greatest fuzzy value. The process of finding the FRP is illustrated with examples.